# /smithery/servers/search

`POST /api/smithery/servers/search`

Price: 20 credits

Search the Smithery registry of MCP servers. Returns each server's registry id, display name, publisher namespace, description, homepage, install count, creation date and its verified, Smithery-managed, remote and deployed flags. Results can be narrowed to verified publishers, to servers Smithery hosts itself, or to one publisher namespace. Omitting `query` browses the whole catalog in relevance order.

## How to use it

Use this to turn a capability description into Smithery server ids that /smithery/servers accepts. Matching is semantic, so a full phrase such as 'send messages to a chat workspace' works better than a single keyword, and the ranking degrades gracefully instead of going empty — a query with no real match still returns a full page of loosely related servers, so judge relevance from the descriptions rather than assuming every row matches. Read `use_count` for adoption and `by_smithery` for who runs the server; `relevance_score` ranks within this one query only and is not a quality rating. Leave `query` out entirely to browse the catalog instead of matching one; neither mode reaches the full 504-row page wall in practice, since a query rarely returns more than ~200 rows and the browse ordering itself repeats content past its first few pages.

## Parameters

- `access-token` (string, required)

## Request body

- `timeout` (integer) — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
- `query` (string, nullable) — What the server should do, or its name. Matching is semantic, so a phrase works as well as a keyword. Leave it out to browse the whole catalog in relevance order (examples: "slack", "read pdf files", "postgres database"; minLength: 1)
- `count` (integer, required) — Max number of results (examples: 21; min: 1; max: 504)
- `verified_only` (boolean) — Keep only servers whose publisher Smithery has verified owns the linked homepage (default: false)
- `smithery_managed_only` (boolean) — Keep only servers Smithery itself hosts and runs, rather than ones it only lists (default: false)
- `namespace` (string, nullable) — Keep only servers published under this owner namespace, as it appears before the slash in a server id (examples: "exa", "smithery-ai"; minLength: 1)

## Response

### 200 — Successful Response

- `@type` (string) (default: "SmitheryServer")
- `id` (string, required)
- `url` (string, required)
- `name` (string, nullable)
- `namespace` (string, nullable)
- `alias` (string, nullable)
- `uuid` (string, nullable)
- `description` (string, nullable)
- `homepage` (string, nullable)
- `icon_url` (string, nullable)
- `owner_id` (string, nullable)
- `use_count` (integer, nullable)
- `relevance_score` (number, nullable)
- `verified` (boolean, nullable)
- `by_smithery` (boolean, nullable)
- `is_deployed` (boolean, nullable)
- `remote` (boolean, nullable)
- `inactive` (boolean, nullable)
- `unlisted` (boolean, nullable)
- `created_at` (string, nullable)

## Errors

### 422 — Validation Error

The request body did not validate

What to do: Check the fields against this schema. A URN with the wrong prefix is the most common cause.

- `detail` (array)
  - `loc` (array, required)
  - `msg` (string, required)
  - `type` (string, required)
  - `input` (any)
  - `ctx` (object)

### 408

The request ran past its time limit

What to do: Raise `timeout` in the request body, up to the maximum this endpoint documents. Lowering `count` or turning off the `with_*` flags also helps, because less work finishes sooner.

### 412

The entity was not found, or a precondition failed

What to do: Retrying will not help: either the entity does not exist, or the input points at a different one.

### 429

Too many requests: a rate limit or a usage window is exhausted

What to do: When the response carries an X-Retry-After header, wait that many seconds and retry: the same number is in the body as `detail.retry_after`, and the limit clears once that window passes. The message in the body names the limit that was hit.

### 500

Something broke on our side

What to do: Retrying will not help. If it keeps happening, send us the X-Request-ID from the response headers.

### 529

Rate limit reached, or the endpoint is overloaded

What to do: Wait at least 30 seconds, then retry.

## Response envelope

Success: Array of objects (may be empty if no results)

Error: Error may coexist with partial results if it occurs mid-execution. Check X-Error header and status code.

Every response carries these headers:

- `X-Error` — Error message text (present only on error)
- `X-Request-ID` — Unique request identifier
- `X-Execution-Time` — Execution time in seconds
- `X-Result-Count` — How many records the body carries. 0 means an empty result, which is a normal answer and not by itself an error. A non-zero count can come back together with X-Error when the failure happened partway through — read this header and X-Error independently.
- `X-Total-Available-Results` — How many records exist for this query, when the endpoint can say. On a `dry_run` request this is the answer and the body is empty. It saturates: the endpoint's documented maximum means 'at least that many', any smaller number is exact.
- `X-Warning` — Present when the request body carried keys this endpoint does not document. They were ignored, so any filter you meant to apply through them did not apply. Check the spelling against this schema and retry.
- `X-Retry-After` — Seconds to wait before retrying. Present only on 429.